Efficient and adaptive design of RBF neural network for maximum energy harvesting from standalone PV system

Abstract

This paper deals with a topical topic, the maximum energy harvest of standalone PV system under varying conditions. It introduces a new approach based on the use of artificial intelligence and machine learning to overcome the usual weaknesses of conventional Maximum Power Point Tracking (MPPT) techniques and to improve solutions to meet growing energy demand and further promote sustainable development. The proposal consists of using Radial Basis Function Neural Network (RBFNN) tuned by a PSO algorithm as MPPT controller. The main aim of this combination (RBFNN-PSO) is to achieve the best compromise between the control accuracy and complexity, while using a simple optimization algorithm. This aim is motivated by the potential of the neural networks to learn from any tasks and to generalize the acquired knowledge to other situation never seen before. The proposal reaches a high efficiency and high energy harvesting with a yield greater than 99 %. The performed comparative study with other intelligent techniques from literature prove the superiority and the promising potential of the introduced approach. The developed work presented in this paper is developed with MatLab/Simulink environment.